aboutsummaryrefslogtreecommitdiff
blob: 689cefa2deb6d2067ad164b072993c7c05cf1925 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
/* Copyright (C) 2002-2013 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Ulrich Drepper <drepper@redhat.com>, 2002.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <http://www.gnu.org/licenses/>.  */

#include <assert.h>
#include <errno.h>
#include <time.h>
#include "pthreadP.h"
#include <lowlevellock.h>
#include <not-cancel.h>

#include <stap-probe.h>

#ifndef lll_timedlock_elision
#define lll_timedlock_elision(a,dummy,b,c) lll_timedlock(a, b, c)
#endif

#ifndef lll_trylock_elision
#define lll_trylock_elision(a,t) lll_trylock(a)
#endif

#ifndef FORCE_ELISION
#define FORCE_ELISION(m, s)
#endif

int
pthread_mutex_timedlock (mutex, abstime)
     pthread_mutex_t *mutex;
     const struct timespec *abstime;
{
  int oldval;
  pid_t id = THREAD_GETMEM (THREAD_SELF, tid);
  int result = 0;

  LIBC_PROBE (mutex_timedlock_entry, 2, mutex, abstime);

  /* We must not check ABSTIME here.  If the thread does not block
     abstime must not be checked for a valid value.  */

  switch (__builtin_expect (PTHREAD_MUTEX_TYPE_ELISION (mutex),
			    PTHREAD_MUTEX_TIMED_NP))
    {
      /* Recursive mutex.  */
    case PTHREAD_MUTEX_RECURSIVE_NP|PTHREAD_MUTEX_ELISION_NP:
    case PTHREAD_MUTEX_RECURSIVE_NP:
      /* Check whether we already hold the mutex.  */
      if (mutex->__data.__owner == id)
	{
	  /* Just bump the counter.  */
	  if (__builtin_expect (mutex->__data.__count + 1 == 0, 0))
	    /* Overflow of the counter.  */
	    return EAGAIN;

	  ++mutex->__data.__count;

	  goto out;
	}

      /* We have to get the mutex.  */
      result = lll_timedlock (mutex->__data.__lock, abstime,
			      PTHREAD_MUTEX_PSHARED (mutex));

      if (result != 0)
	goto out;

      /* Only locked once so far.  */
      mutex->__data.__count = 1;
      break;

      /* Error checking mutex.  */
    case PTHREAD_MUTEX_ERRORCHECK_NP:
      /* Check whether we already hold the mutex.  */
      if (__builtin_expect (mutex->__data.__owner == id, 0))
	return EDEADLK;

      /* FALLTHROUGH */

    case PTHREAD_MUTEX_TIMED_NP:
      FORCE_ELISION (mutex, goto elision);
    simple:
      /* Normal mutex.  */
      result = lll_timedlock (mutex->__data.__lock, abstime,
			      PTHREAD_MUTEX_PSHARED (mutex));
      break;

    case PTHREAD_MUTEX_TIMED_ELISION_NP:
    elision: __attribute__((unused))
      /* Don't record ownership */
      return lll_timedlock_elision (mutex->__data.__lock,
				    mutex->__data.__spins,
				    abstime,
				    PTHREAD_MUTEX_PSHARED (mutex));


    case PTHREAD_MUTEX_ADAPTIVE_NP:
      if (! __is_smp)
	goto simple;

      if (lll_trylock (mutex->__data.__lock) != 0)
	{
	  int cnt = 0;
	  int max_cnt = MIN (MAX_ADAPTIVE_COUNT,
			     mutex->__data.__spins * 2 + 10);
	  do
	    {
	      if (cnt++ >= max_cnt)
		{
		  result = lll_timedlock (mutex->__data.__lock, abstime,
					  PTHREAD_MUTEX_PSHARED (mutex));
		  break;
		}

#ifdef BUSY_WAIT_NOP
	      BUSY_WAIT_NOP;
#endif
	    }
	  while (lll_trylock (mutex->__data.__lock) != 0);

	  mutex->__data.__spins += (cnt - mutex->__data.__spins) / 8;
	}
      break;

    case PTHREAD_MUTEX_ROBUST_RECURSIVE_NP:
    case PTHREAD_MUTEX_ROBUST_ERRORCHECK_NP:
    case PTHREAD_MUTEX_ROBUST_NORMAL_NP:
    case PTHREAD_MUTEX_ROBUST_ADAPTIVE_NP:
      THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending,
		     &mutex->__data.__list.__next);

      oldval = mutex->__data.__lock;
      do
	{
	again:
	  if ((oldval & FUTEX_OWNER_DIED) != 0)
	    {
	      /* The previous owner died.  Try locking the mutex.  */
	      int newval = id | (oldval & FUTEX_WAITERS);

	      newval
		= atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
						       newval, oldval);
	      if (newval != oldval)
		{
		  oldval = newval;
		  goto again;
		}

	      /* We got the mutex.  */
	      mutex->__data.__count = 1;
	      /* But it is inconsistent unless marked otherwise.  */
	      mutex->__data.__owner = PTHREAD_MUTEX_INCONSISTENT;

	      ENQUEUE_MUTEX (mutex);
	      THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);

	      /* Note that we deliberately exit here.  If we fall
		 through to the end of the function __nusers would be
		 incremented which is not correct because the old
		 owner has to be discounted.  */
	      return EOWNERDEAD;
	    }

	  /* Check whether we already hold the mutex.  */
	  if (__builtin_expect ((oldval & FUTEX_TID_MASK) == id, 0))
	    {
	      int kind = PTHREAD_MUTEX_TYPE (mutex);
	      if (kind == PTHREAD_MUTEX_ROBUST_ERRORCHECK_NP)
		{
		  THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending,
				 NULL);
		  return EDEADLK;
		}

	      if (kind == PTHREAD_MUTEX_ROBUST_RECURSIVE_NP)
		{
		  THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending,
				 NULL);

		  /* Just bump the counter.  */
		  if (__builtin_expect (mutex->__data.__count + 1 == 0, 0))
		    /* Overflow of the counter.  */
		    return EAGAIN;

		  ++mutex->__data.__count;

		  LIBC_PROBE (mutex_timedlock_acquired, 1, mutex);

		  return 0;
		}
	    }

	  result = lll_robust_timedlock (mutex->__data.__lock, abstime, id,
					 PTHREAD_ROBUST_MUTEX_PSHARED (mutex));

	  if (__builtin_expect (mutex->__data.__owner
				== PTHREAD_MUTEX_NOTRECOVERABLE, 0))
	    {
	      /* This mutex is now not recoverable.  */
	      mutex->__data.__count = 0;
	      lll_unlock (mutex->__data.__lock,
			  PTHREAD_ROBUST_MUTEX_PSHARED (mutex));
	      THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
	      return ENOTRECOVERABLE;
	    }

	  if (result == ETIMEDOUT || result == EINVAL)
	    goto out;

	  oldval = result;
	}
      while ((oldval & FUTEX_OWNER_DIED) != 0);

      mutex->__data.__count = 1;
      ENQUEUE_MUTEX (mutex);
      THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
      break;

    case PTHREAD_MUTEX_PI_RECURSIVE_NP:
    case PTHREAD_MUTEX_PI_ERRORCHECK_NP:
    case PTHREAD_MUTEX_PI_NORMAL_NP:
    case PTHREAD_MUTEX_PI_ADAPTIVE_NP:
    case PTHREAD_MUTEX_PI_ROBUST_RECURSIVE_NP:
    case PTHREAD_MUTEX_PI_ROBUST_ERRORCHECK_NP:
    case PTHREAD_MUTEX_PI_ROBUST_NORMAL_NP:
    case PTHREAD_MUTEX_PI_ROBUST_ADAPTIVE_NP:
      {
	int kind = mutex->__data.__kind & PTHREAD_MUTEX_KIND_MASK_NP;
	int robust = mutex->__data.__kind & PTHREAD_MUTEX_ROBUST_NORMAL_NP;

	if (robust)
	  /* Note: robust PI futexes are signaled by setting bit 0.  */
	  THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending,
			 (void *) (((uintptr_t) &mutex->__data.__list.__next)
				   | 1));

	oldval = mutex->__data.__lock;

	/* Check whether we already hold the mutex.  */
	if (__builtin_expect ((oldval & FUTEX_TID_MASK) == id, 0))
	  {
	    if (kind == PTHREAD_MUTEX_ERRORCHECK_NP)
	      {
		THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
		return EDEADLK;
	      }

	    if (kind == PTHREAD_MUTEX_RECURSIVE_NP)
	      {
		THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);

		/* Just bump the counter.  */
		if (__builtin_expect (mutex->__data.__count + 1 == 0, 0))
		  /* Overflow of the counter.  */
		  return EAGAIN;

		++mutex->__data.__count;

		LIBC_PROBE (mutex_timedlock_acquired, 1, mutex);

		return 0;
	      }
	  }

	oldval = atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
						      id, 0);

	if (oldval != 0)
	  {
	    /* The mutex is locked.  The kernel will now take care of
	       everything.  The timeout value must be a relative value.
	       Convert it.  */
	    int private = (robust
			   ? PTHREAD_ROBUST_MUTEX_PSHARED (mutex)
			   : PTHREAD_MUTEX_PSHARED (mutex));
	    INTERNAL_SYSCALL_DECL (__err);

	    int e = INTERNAL_SYSCALL (futex, __err, 4, &mutex->__data.__lock,
				      __lll_private_flag (FUTEX_LOCK_PI,
							  private), 1,
				      abstime);
	    if (INTERNAL_SYSCALL_ERROR_P (e, __err))
	      {
		if (INTERNAL_SYSCALL_ERRNO (e, __err) == ETIMEDOUT)
		  return ETIMEDOUT;

		if (INTERNAL_SYSCALL_ERRNO (e, __err) == ESRCH
		    || INTERNAL_SYSCALL_ERRNO (e, __err) == EDEADLK)
		  {
		    assert (INTERNAL_SYSCALL_ERRNO (e, __err) != EDEADLK
			    || (kind != PTHREAD_MUTEX_ERRORCHECK_NP
				&& kind != PTHREAD_MUTEX_RECURSIVE_NP));
		    /* ESRCH can happen only for non-robust PI mutexes where
		       the owner of the lock died.  */
		    assert (INTERNAL_SYSCALL_ERRNO (e, __err) != ESRCH
			    || !robust);

		    /* Delay the thread until the timeout is reached.
		       Then return ETIMEDOUT.  */
		    struct timespec reltime;
		    struct timespec now;

		    INTERNAL_SYSCALL (clock_gettime, __err, 2, CLOCK_REALTIME,
				      &now);
		    reltime.tv_sec = abstime->tv_sec - now.tv_sec;
		    reltime.tv_nsec = abstime->tv_nsec - now.tv_nsec;
		    if (reltime.tv_nsec < 0)
		      {
			reltime.tv_nsec += 1000000000;
			--reltime.tv_sec;
		      }
		    if (reltime.tv_sec >= 0)
		      while (nanosleep_not_cancel (&reltime, &reltime) != 0)
			continue;

		    return ETIMEDOUT;
		  }

		return INTERNAL_SYSCALL_ERRNO (e, __err);
	      }

	    oldval = mutex->__data.__lock;

	    assert (robust || (oldval & FUTEX_OWNER_DIED) == 0);
	  }

	if (__builtin_expect (oldval & FUTEX_OWNER_DIED, 0))
	  {
	    atomic_and (&mutex->__data.__lock, ~FUTEX_OWNER_DIED);

	    /* We got the mutex.  */
	    mutex->__data.__count = 1;
	    /* But it is inconsistent unless marked otherwise.  */
	    mutex->__data.__owner = PTHREAD_MUTEX_INCONSISTENT;

	    ENQUEUE_MUTEX_PI (mutex);
	    THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);

	    /* Note that we deliberately exit here.  If we fall
	       through to the end of the function __nusers would be
	       incremented which is not correct because the old owner
	       has to be discounted.  */
	    return EOWNERDEAD;
	  }

	if (robust
	    && __builtin_expect (mutex->__data.__owner
				 == PTHREAD_MUTEX_NOTRECOVERABLE, 0))
	  {
	    /* This mutex is now not recoverable.  */
	    mutex->__data.__count = 0;

	    INTERNAL_SYSCALL_DECL (__err);
	    INTERNAL_SYSCALL (futex, __err, 4, &mutex->__data.__lock,
			      __lll_private_flag (FUTEX_UNLOCK_PI,
						  PTHREAD_ROBUST_MUTEX_PSHARED (mutex)),
			      0, 0);

	    THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
	    return ENOTRECOVERABLE;
	  }

	mutex->__data.__count = 1;
	if (robust)
	  {
	    ENQUEUE_MUTEX_PI (mutex);
	    THREAD_SETMEM (THREAD_SELF, robust_head.list_op_pending, NULL);
	  }
	}
      break;

    case PTHREAD_MUTEX_PP_RECURSIVE_NP:
    case PTHREAD_MUTEX_PP_ERRORCHECK_NP:
    case PTHREAD_MUTEX_PP_NORMAL_NP:
    case PTHREAD_MUTEX_PP_ADAPTIVE_NP:
      {
	int kind = mutex->__data.__kind & PTHREAD_MUTEX_KIND_MASK_NP;

	oldval = mutex->__data.__lock;

	/* Check whether we already hold the mutex.  */
	if (mutex->__data.__owner == id)
	  {
	    if (kind == PTHREAD_MUTEX_ERRORCHECK_NP)
	      return EDEADLK;

	    if (kind == PTHREAD_MUTEX_RECURSIVE_NP)
	      {
		/* Just bump the counter.  */
		if (__builtin_expect (mutex->__data.__count + 1 == 0, 0))
		  /* Overflow of the counter.  */
		  return EAGAIN;

		++mutex->__data.__count;

		LIBC_PROBE (mutex_timedlock_acquired, 1, mutex);

		return 0;
	      }
	  }

	int oldprio = -1, ceilval;
	do
	  {
	    int ceiling = (oldval & PTHREAD_MUTEX_PRIO_CEILING_MASK)
			  >> PTHREAD_MUTEX_PRIO_CEILING_SHIFT;

	    if (__pthread_current_priority () > ceiling)
	      {
		result = EINVAL;
	      failpp:
		if (oldprio != -1)
		  __pthread_tpp_change_priority (oldprio, -1);
		return result;
	      }

	    result = __pthread_tpp_change_priority (oldprio, ceiling);
	    if (result)
	      return result;

	    ceilval = ceiling << PTHREAD_MUTEX_PRIO_CEILING_SHIFT;
	    oldprio = ceiling;

	    oldval
	      = atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
						     ceilval | 1, ceilval);

	    if (oldval == ceilval)
	      break;

	    do
	      {
		oldval
		  = atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
							 ceilval | 2,
							 ceilval | 1);

		if ((oldval & PTHREAD_MUTEX_PRIO_CEILING_MASK) != ceilval)
		  break;

		if (oldval != ceilval)
		  {
		    /* Reject invalid timeouts.  */
		    if (abstime->tv_nsec < 0 || abstime->tv_nsec >= 1000000000)
		      {
			result = EINVAL;
			goto failpp;
		      }

		    struct timeval tv;
		    struct timespec rt;

		    /* Get the current time.  */
		    (void) __gettimeofday (&tv, NULL);

		    /* Compute relative timeout.  */
		    rt.tv_sec = abstime->tv_sec - tv.tv_sec;
		    rt.tv_nsec = abstime->tv_nsec - tv.tv_usec * 1000;
		    if (rt.tv_nsec < 0)
		      {
			rt.tv_nsec += 1000000000;
			--rt.tv_sec;
		      }

		    /* Already timed out?  */
		    if (rt.tv_sec < 0)
		      {
			result = ETIMEDOUT;
			goto failpp;
		      }

		    lll_futex_timed_wait (&mutex->__data.__lock,
					  ceilval | 2, &rt,
					  PTHREAD_MUTEX_PSHARED (mutex));
		  }
	      }
	    while (atomic_compare_and_exchange_val_acq (&mutex->__data.__lock,
							ceilval | 2, ceilval)
		   != ceilval);
	  }
	while ((oldval & PTHREAD_MUTEX_PRIO_CEILING_MASK) != ceilval);

	assert (mutex->__data.__owner == 0);
	mutex->__data.__count = 1;
      }
      break;

    default:
      /* Correct code cannot set any other type.  */
      return EINVAL;
    }

  if (result == 0)
    {
      /* Record the ownership.  */
      mutex->__data.__owner = id;
      ++mutex->__data.__nusers;

      LIBC_PROBE (mutex_timedlock_acquired, 1, mutex);
    }

 out:
  return result;
}